tighten-prose

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches an updated list of AI writing patterns from a public Wikipedia API endpoint (en.wikipedia.org). This is a well-known service and the request is used to retrieve data for linguistic analysis rather than executable code.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from an external source (Wikipedia) to build its vocabulary list. While this represents a theoretical injection surface if the source page were compromised, the risk is minimal because the skill lacks dangerous capabilities such as file system modification, command execution, or network exfiltration, and the ingestion is scoped to extracting vocabulary words.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:14 AM
Security Audit — agent-trust-hub — tighten-prose